© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143789
    Prev
    Next
    INDEX
    Explanations

    dumpster because

    np_acts-logits-general · gemini-2.5-flash-lite

    "IT", "article", "to", "and", ",", "dependent", "How"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    L
    0.47
    Text
    0.44
    Cost
    0.44
    Pune
    0.44
    燕
    0.44
    骚
    0.44
    皇后
    0.43
    Nigerian
    0.43
    「
    0.43
    Surprisingly
    0.43
    POSITIVE LOGITS
     RESERVE
    0.54
     promul
    0.54
     അവരുടെ
    0.51
     circumst
    0.47
     hb
    0.47
     DISPLAYS
    0.47
     dẫn
    0.46
     ayrıca
    0.46
     ปลา
    0.46
     SD
    0.46
    Activations Density 0.001%

    No Known Activations